@inproceedings{wood-doughty-etal-2021-using,
    title = "Using Noisy Self-Reports to Predict {T}witter User Demographics",
    author = "Wood-Doughty, Zach  and
      Xu, Paiheng  and
      Liu, Xiao  and
      Dredze, Mark",
    editor = "Ku, Lun-Wei  and
      Li, Cheng-Te",
    booktitle = "Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.socialnlp-1.11/",
    doi = "10.18653/v1/2021.socialnlp-1.11",
    pages = "123--137",
    abstract = "Computational social science studies often contextualize content analysis within standard demographics. Since demographics are unavailable on many social media platforms (e.g. Twitter), numerous studies have inferred demographics automatically. Despite many studies presenting proof-of-concept inference of race and ethnicity, training of practical systems remains elusive since there are few annotated datasets. Existing datasets are small, inaccurate, or fail to cover the four most common racial and ethnic groups in the United States. We present a method to identify self-reports of race and ethnicity from Twitter profile descriptions. Despite the noise of automated supervision, our self-report datasets enable improvements in classification performance on gold standard self-report survey data. The result is a reproducible method for creating large-scale training resources for race and ethnicity."
}